提出首个考虑方差的神经上下文双人赌博机算法，显著降低网络宽度需求。
Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
- 用浅层探索+神经网络逼近非线性效用函数
- 理论证明网络宽度仅需T⁶量级，实现次线性后悔率
- 适合高维非线性推荐与个性化决策场景
我们首次为上下文双人赌博机设计了方差感知算法，采用神经网络进行非线性效用近似，并结合浅层探索策略。以往工作因缺乏闭式估计器，要求网络宽度极大（m = ~Ω(T¹⁴)）。本文通过迭代自提升与谱分析相结合的新方法，将所需网络宽度降至m = ~Ω(T⁶)，并在UCB与TS框架下证明算法达到次线性后悔率~O(d√(∑σₜ²) + √dT)。实验表明，该算法在合成与真实数据集上均具计算高效性、次线性后悔表现及领先性能。
原文摘要 · Abstract (English)
We introduce the first variance-aware algorithms for contextual dueling bandits that leverage shallow exploration strategies with neural networks for nonlinear utility approximation. A key theoretical challenge is the absence of a closed-form estimator, which led prior work to require an extremely large network width $m$ (i.e., $m = \widetildeΩ(T^{14})$). We address this constraint with a novel analytical approach that combines iterative self-improvement with spectral analysis. Our analysis significantly reduces the network width requirement to $m = \widetildeΩ(T^{6})$, and shows that our algorithms achieve a sublinear regret of $\widetilde{\mathcal{O}}(d\sqrt{\sum_{t=1}^{T} σ_t^2} + \sqrt{dT})$ under both UCB and TS frameworks. Empirical results show that the proposed algorithms are not only computationally efficient and exhibit sublinear regret in practical settings, but also achieve state-of-the-art performance on both synthetic and real-world tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。